We propose DeepExplorer, a simple and lightweight metric-free exploration method for topological mapping of unknown environments. It performs task and motion planning (TAMP) entirely in image feature space. The task planner is a recurrent network using the latest image observation sequence to hallucinate a feature as the next-best exploration goal. The motion planner then utilizes the current and the hallucinated features to generate an action taking the agent towards that goal. The two planners are jointly trained via deeply-supervised imitation learning from expert demonstrations. During exploration, we iteratively call the two planners to predict the next action, and the topological map is built by constantly appending the latest image observation and action to the map and using visual place recognition (VPR) for loop closing. The resulting topological map efficiently represents an environment's connectivity and traversability, so it can be used for tasks such as visual navigation. We show DeepExplorer's exploration efficiency and strong sim2sim generalization capability on large-scale simulation datasets like Gibson and MP3D. Its effectiveness is further validated via the image-goal navigation performance on the resulting topological map. We further show its strong zero-shot sim2real generalization capability in real-world experiments. The source code is available at \url{https://ai4ce.github.io/DeepExplorer/}.

翻译：我们提出DeepExplorer，一种简单轻量的无度量探索方法，用于未知环境的拓扑地图构建。该方法完全在图像特征空间中执行任务与运动规划（TAMP）。任务规划器采用循环网络，利用最新图像观测序列来“幻觉”出一个特征作为下一最佳探索目标。运动规划器则利用当前特征与幻觉特征生成一个动作，驱动智能体朝向该目标移动。两个规划器通过专家示教的深度监督模仿学习进行联合训练。在探索过程中，我们迭代调用两个规划器预测下一动作，并通过不断向地图追加最新图像观测和动作以及利用视觉地点识别（VPR）进行闭环检测来构建拓扑地图。生成的拓扑地图高效地表达了环境的连通性和可通行性，因此可用于视觉导航等任务。我们展示了DeepExplorer在Gibson和MP3D等大规模仿真数据集上的探索效率与强大的sim2sim泛化能力。通过基于所得拓扑地图的图像目标导航性能进一步验证了其有效性。此外，我们还在真实世界实验中展示了其强大的零样本sim2real泛化能力。源代码见\url{https://ai4ce.github.io/DeepExplorer/}。